© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27021
    Prev
    Next
    INDEX
    Explanations

    doing / actions and their objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amat
    -0.09
    èĴ¿
    -0.08
    еÑĢ
    -0.08
    pei
    -0.08
    å°ıåѦçĶŁ
    -0.08
    éĥ½æĥ³
    -0.08
    RIPT
    -0.08
    磶
    -0.08
    ãĥ³ãĤ°
    -0.08
    ä¹Łå¥½
    -0.07
    POSITIVE LOGITS
     ÑĤомÑĥ
    0.10
    èµ°ä¸ĭåİ»
    0.09
    å½ĵä¹ĭ
    0.09
    ReturnValue
    0.09
    æ¬
    0.09
    åĿı
    0.09
     Nice
    0.09
    iona
    0.08
    apan
    0.08
    indle
    0.08
    Activations Density 0.155%

    No Known Activations